© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8580
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure, particularly involving function definitions and file paths

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -1.02
    featureID
    -0.93
     disambiguazione
    -0.77
    RegistryLite
    -0.75
     ویکی‌پدیا
    -0.74
    
    -0.72
     snippetHide
    -0.71
     المعيارى
    -0.69
    DockStyle
    -0.68
     <<<<<<<<<<<<<<
    -0.68
    POSITIVE LOGITS
    的问道
    0.53
     Dam
    0.50
    地说道
    0.50
    뀐
    0.50
     Sun
    0.49
    Dam
    0.49
    pert
    0.48
    enters
    0.48
    Sun
    0.46
    뀌
    0.46
    Activations Density 0.253%

    No Known Activations